Analysis of Covid-19

Getting Data

df_confirmed <- read_csv("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv")
df_deaths <- read_csv("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_deaths_global.csv")
df_recovered <- read_csv("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_recovered_global.csv")

df_confirmed <- df_confirmed%>%
  pivot_longer(cols = c(-`Province/State`, -`Country/Region`, -Lat, -Long), names_to = "Date")
df_confirmed <- rename(df_confirmed, Confirmed = value)

df_deaths <- df_deaths%>%
  pivot_longer(cols = c(-`Province/State`, -`Country/Region`, -Lat, -Long), names_to = "Date")

df_recovered <- df_recovered%>%
  pivot_longer(cols = c(-`Province/State`, -`Country/Region`, -Lat, -Long), names_to = "Date")

covid <- df_confirmed %>%
  left_join(select(df_deaths, -Lat, -Long, Deaths = value))%>%
  left_join(select(df_recovered, -Lat, -Long, Recovered = value))
covid$Date <- lubridate::mdy(covid$Date)

covid <- covid%>%
  group_by(`Country/Region`, `Province/State`)%>%
  mutate(new_confirmed = Confirmed - lag(Confirmed, n=1, order_by = Date))%>%
  mutate(new_deaths = Deaths - lag(Deaths, n=1, order_by = Date))%>%
  mutate(new_recovered = Recovered - lag(Recovered, n=1, order_by = Date))%>%
  ungroup()

covid[4000:4005, ]

## # A tibble: 6 x 11
##   `Province/State` `Country/Region`   Lat  Long Date       Confirmed Deaths
##   <chr>            <chr>            <dbl> <dbl> <date>         <dbl>  <dbl>
## 1 Hainan           China             19.2  110. 2020-01-31        52      1
## 2 Hainan           China             19.2  110. 2020-02-01        62      1
## 3 Hainan           China             19.2  110. 2020-02-02        64      1
## 4 Hainan           China             19.2  110. 2020-02-03        72      1
## 5 Hainan           China             19.2  110. 2020-02-04        80      1
## 6 Hainan           China             19.2  110. 2020-02-05        99      1
## # ... with 4 more variables: Recovered <dbl>, new_confirmed <dbl>,
## #   new_deaths <dbl>, new_recovered <dbl>

Analyse Data

q<- covid%>%
  ungroup()%>%
  group_by(Date)%>%
  summarise(Confirmed = sum(Confirmed), Recovered=sum(Recovered, na.rm=TRUE), Deaths=sum(Deaths))%>%
  ggplot(aes(Date, `All Cases`))+
    geom_col(aes(x = Date, y = Confirmed))+
    geom_col(aes(x = Date, y = Recovered), color = "green")+
    geom_col(aes(x = Date, y = Deaths), color = "red")+
    labs(title = "Total Cases Worldwide")

plotly::ggplotly(q)

covid%>%
  filter(`Country/Region` %in% c("Germany", "US", "Italy", "China"))%>%
    ggplot(aes(Date, `New Cases`))+
      geom_col(aes(x = Date, y= new_confirmed))+
      geom_line(aes(x = Date, y= new_recovered), color = "green", size = 1)+
      geom_line(aes(x = Date, y= new_deaths), color = "red", size = 1)+
      labs(title = "Daily Reportet New Cases")+
      facet_wrap(~ `Country/Region`)

#     alt.: facet_grid(rows = vars(`Country/Region`))